| { |
| "model_type": "intern_s2_preview", |
| "architectures": [ |
| "InternS2PreviewForConditionalGeneration" |
| ], |
| "transformers_version": "5.2.0", |
| "auto_map": { |
| "AutoConfig": "configuration_interns2_preview.InternS2PreviewConfig", |
| "AutoModelForCausalLM": "modeling_interns2_preview.InternS2PreviewForCausalLM", |
| "AutoModel": "modeling_interns2_preview.InternS2PreviewModel", |
| "AutoModelForImageTextToText": "modeling_interns2_preview.InternS2PreviewForConditionalGeneration", |
| "AutoModelForMultimodalLM": "modeling_interns2_preview.InternS2PreviewForConditionalGeneration" |
| }, |
| "image_token_id": 248056, |
| "text_config": { |
| "model_type": "qwen3_5_moe_text", |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_output_gate": true, |
| "dtype": "bfloat16", |
| "eos_token_id": 248044, |
| "full_attention_interval": 4, |
| "head_dim": 256, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "layer_types": [ |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention" |
| ], |
| "linear_conv_kernel_dim": 4, |
| "linear_key_head_dim": 128, |
| "linear_num_key_heads": 16, |
| "linear_num_value_heads": 32, |
| "linear_value_head_dim": 128, |
| "max_position_embeddings": 262144, |
| "mlp_only_layers": [], |
| "moe_intermediate_size": 512, |
| "mtp_num_hidden_layers": 1, |
| "mtp_use_dedicated_embeddings": false, |
| "num_attention_heads": 16, |
| "num_experts": 256, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 2, |
| "rms_norm_eps": 1e-06, |
| "router_aux_loss_coef": 0.001, |
| "shared_expert_intermediate_size": 512, |
| "use_cache": true, |
| "vocab_size": 251392, |
| "mamba_ssm_dtype": "float32", |
| "rope_parameters": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 11, |
| 11, |
| 10 |
| ], |
| "rope_type": "default", |
| "rope_theta": 10000000, |
| "partial_rotary_factor": 0.25 |
| }, |
| "pad_token_id": null, |
| "bos_token_id": null, |
| "tie_word_embeddings": false, |
| "output_router_logits": false, |
| "partial_rotary_factor": 0.25 |
| }, |
| "tie_word_embeddings": false, |
| "video_token_id": 248057, |
| "vision_config": { |
| "model_type": "intern_s2_preview", |
| "deepstack_visual_indexes": [], |
| "depth": 27, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "in_channels": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 4304, |
| "num_heads": 16, |
| "num_position_embeddings": 2304, |
| "out_hidden_size": 2048, |
| "patch_size": 16, |
| "spatial_merge_size": 2, |
| "temporal_patch_size": 2 |
| }, |
| "vision_end_token_id": 248054, |
| "vision_start_token_id": 248053, |
| "ts_config": { |
| "model_type": "interns2_preview_time_series", |
| "auto_map": { |
| "AutoConfig": "configuration_interns2_preview.InternS2PreviewTimeSeriesConfig", |
| "AutoModel": "modeling_interns2_preview.InternS2PreviewTimeSeriesModel" |
| }, |
| "activation_dropout": 0.0, |
| "activation_function": "gelu", |
| "attention_dropout": 0.0, |
| "d_model": 768, |
| "dropout": 0.0, |
| "encoder_attention_heads": 8, |
| "encoder_ffn_dim": 3072, |
| "encoder_layerdrop": 0.0, |
| "encoder_layers": 17, |
| "max_source_positions": 1500, |
| "num_mel_bins": 80, |
| "out_hidden_size": 2048, |
| "scale_embedding": false, |
| "ts_adapt_in_dim": 256, |
| "ts_adapt_out_dim": 1024, |
| "ts_hidden_dim": 1024 |
| }, |
| "ts_token_id": 248093, |
| "ts_start_id": 248091, |
| "ts_end_id": 248092, |
| "quantization_config": { |
| "activation_scheme": "dynamic", |
| "fmt": "e4m3", |
| "quant_method": "fp8", |
| "scale_fmt": "ue8m0", |
| "weight_block_size": [ |
| 128, |
| 128 |
| ], |
| "modules_to_not_convert": [ |
| "lm_head", |
| "model.language_model.embed_tokens", |
| "model.language_model.layers.0.input_layernorm", |
| "model.language_model.layers.0.linear_attn", |
| "model.language_model.layers.0.linear_attn.conv1d", |
| "model.language_model.layers.0.linear_attn.in_proj_a", |
| "model.language_model.layers.0.linear_attn.in_proj_b", |
| "model.language_model.layers.0.linear_attn.norm", |
| "model.language_model.layers.0.mlp.gate", |
| "model.language_model.layers.0.mlp.shared_expert_gate", |
| "model.language_model.layers.0.post_attention_layernorm", |
| "model.language_model.layers.1.input_layernorm", |
| "model.language_model.layers.1.linear_attn", |
| "model.language_model.layers.1.linear_attn.conv1d", |
| "model.language_model.layers.1.linear_attn.in_proj_a", |
| "model.language_model.layers.1.linear_attn.in_proj_b", |
| "model.language_model.layers.1.linear_attn.norm", |
| "model.language_model.layers.1.mlp.gate", |
| "model.language_model.layers.1.mlp.shared_expert_gate", |
| "model.language_model.layers.1.post_attention_layernorm", |
| "model.language_model.layers.10.input_layernorm", |
| "model.language_model.layers.10.linear_attn", |
| "model.language_model.layers.10.linear_attn.conv1d", |
| "model.language_model.layers.10.linear_attn.in_proj_a", |
| "model.language_model.layers.10.linear_attn.in_proj_b", |
| "model.language_model.layers.10.linear_attn.norm", |
| "model.language_model.layers.10.mlp.gate", |
| "model.language_model.layers.10.mlp.shared_expert_gate", |
| "model.language_model.layers.10.post_attention_layernorm", |
| "model.language_model.layers.11.input_layernorm", |
| "model.language_model.layers.11.mlp.gate", |
| "model.language_model.layers.11.mlp.shared_expert_gate", |
| "model.language_model.layers.11.post_attention_layernorm", |
| "model.language_model.layers.11.self_attn.k_norm", |
| "model.language_model.layers.11.self_attn.q_norm", |
| "model.language_model.layers.12.input_layernorm", |
| "model.language_model.layers.12.linear_attn", |
| "model.language_model.layers.12.linear_attn.conv1d", |
| "model.language_model.layers.12.linear_attn.in_proj_a", |
| "model.language_model.layers.12.linear_attn.in_proj_b", |
| "model.language_model.layers.12.linear_attn.norm", |
| "model.language_model.layers.12.mlp.gate", |
| "model.language_model.layers.12.mlp.shared_expert_gate", |
| "model.language_model.layers.12.post_attention_layernorm", |
| "model.language_model.layers.13.input_layernorm", |
| "model.language_model.layers.13.linear_attn", |
| "model.language_model.layers.13.linear_attn.conv1d", |
| "model.language_model.layers.13.linear_attn.in_proj_a", |
| "model.language_model.layers.13.linear_attn.in_proj_b", |
| "model.language_model.layers.13.linear_attn.norm", |
| "model.language_model.layers.13.mlp.gate", |
| "model.language_model.layers.13.mlp.shared_expert_gate", |
| "model.language_model.layers.13.post_attention_layernorm", |
| "model.language_model.layers.14.input_layernorm", |
| "model.language_model.layers.14.linear_attn", |
| "model.language_model.layers.14.linear_attn.conv1d", |
| "model.language_model.layers.14.linear_attn.in_proj_a", |
| "model.language_model.layers.14.linear_attn.in_proj_b", |
| "model.language_model.layers.14.linear_attn.norm", |
| "model.language_model.layers.14.mlp.gate", |
| "model.language_model.layers.14.mlp.shared_expert_gate", |
| "model.language_model.layers.14.post_attention_layernorm", |
| "model.language_model.layers.15.input_layernorm", |
| "model.language_model.layers.15.mlp.gate", |
| "model.language_model.layers.15.mlp.shared_expert_gate", |
| "model.language_model.layers.15.post_attention_layernorm", |
| "model.language_model.layers.15.self_attn.k_norm", |
| "model.language_model.layers.15.self_attn.q_norm", |
| "model.language_model.layers.16.input_layernorm", |
| "model.language_model.layers.16.linear_attn", |
| "model.language_model.layers.16.linear_attn.conv1d", |
| "model.language_model.layers.16.linear_attn.in_proj_a", |
| "model.language_model.layers.16.linear_attn.in_proj_b", |
| "model.language_model.layers.16.linear_attn.norm", |
| "model.language_model.layers.16.mlp.gate", |
| "model.language_model.layers.16.mlp.shared_expert_gate", |
| "model.language_model.layers.16.post_attention_layernorm", |
| "model.language_model.layers.17.input_layernorm", |
| "model.language_model.layers.17.linear_attn", |
| "model.language_model.layers.17.linear_attn.conv1d", |
| "model.language_model.layers.17.linear_attn.in_proj_a", |
| "model.language_model.layers.17.linear_attn.in_proj_b", |
| "model.language_model.layers.17.linear_attn.norm", |
| "model.language_model.layers.17.mlp.gate", |
| "model.language_model.layers.17.mlp.shared_expert_gate", |
| "model.language_model.layers.17.post_attention_layernorm", |
| "model.language_model.layers.18.input_layernorm", |
| "model.language_model.layers.18.linear_attn", |
| "model.language_model.layers.18.linear_attn.conv1d", |
| "model.language_model.layers.18.linear_attn.in_proj_a", |
| "model.language_model.layers.18.linear_attn.in_proj_b", |
| "model.language_model.layers.18.linear_attn.norm", |
| "model.language_model.layers.18.mlp.gate", |
| "model.language_model.layers.18.mlp.shared_expert_gate", |
| "model.language_model.layers.18.post_attention_layernorm", |
| "model.language_model.layers.19.input_layernorm", |
| "model.language_model.layers.19.mlp.gate", |
| "model.language_model.layers.19.mlp.shared_expert_gate", |
| "model.language_model.layers.19.post_attention_layernorm", |
| "model.language_model.layers.19.self_attn.k_norm", |
| "model.language_model.layers.19.self_attn.q_norm", |
| "model.language_model.layers.2.input_layernorm", |
| "model.language_model.layers.2.linear_attn", |
| "model.language_model.layers.2.linear_attn.conv1d", |
| "model.language_model.layers.2.linear_attn.in_proj_a", |
| "model.language_model.layers.2.linear_attn.in_proj_b", |
| "model.language_model.layers.2.linear_attn.norm", |
| "model.language_model.layers.2.mlp.gate", |
| "model.language_model.layers.2.mlp.shared_expert_gate", |
| "model.language_model.layers.2.post_attention_layernorm", |
| "model.language_model.layers.20.input_layernorm", |
| "model.language_model.layers.20.linear_attn", |
| "model.language_model.layers.20.linear_attn.conv1d", |
| "model.language_model.layers.20.linear_attn.in_proj_a", |
| "model.language_model.layers.20.linear_attn.in_proj_b", |
| "model.language_model.layers.20.linear_attn.norm", |
| "model.language_model.layers.20.mlp.gate", |
| "model.language_model.layers.20.mlp.shared_expert_gate", |
| "model.language_model.layers.20.post_attention_layernorm", |
| "model.language_model.layers.21.input_layernorm", |
| "model.language_model.layers.21.linear_attn", |
| "model.language_model.layers.21.linear_attn.conv1d", |
| "model.language_model.layers.21.linear_attn.in_proj_a", |
| "model.language_model.layers.21.linear_attn.in_proj_b", |
| "model.language_model.layers.21.linear_attn.norm", |
| "model.language_model.layers.21.mlp.gate", |
| "model.language_model.layers.21.mlp.shared_expert_gate", |
| "model.language_model.layers.21.post_attention_layernorm", |
| "model.language_model.layers.22.input_layernorm", |
| "model.language_model.layers.22.linear_attn", |
| "model.language_model.layers.22.linear_attn.conv1d", |
| "model.language_model.layers.22.linear_attn.in_proj_a", |
| "model.language_model.layers.22.linear_attn.in_proj_b", |
| "model.language_model.layers.22.linear_attn.norm", |
| "model.language_model.layers.22.mlp.gate", |
| "model.language_model.layers.22.mlp.shared_expert_gate", |
| "model.language_model.layers.22.post_attention_layernorm", |
| "model.language_model.layers.23.input_layernorm", |
| "model.language_model.layers.23.mlp.gate", |
| "model.language_model.layers.23.mlp.shared_expert_gate", |
| "model.language_model.layers.23.post_attention_layernorm", |
| "model.language_model.layers.23.self_attn.k_norm", |
| "model.language_model.layers.23.self_attn.q_norm", |
| "model.language_model.layers.24.input_layernorm", |
| "model.language_model.layers.24.linear_attn", |
| "model.language_model.layers.24.linear_attn.conv1d", |
| "model.language_model.layers.24.linear_attn.in_proj_a", |
| "model.language_model.layers.24.linear_attn.in_proj_b", |
| "model.language_model.layers.24.linear_attn.norm", |
| "model.language_model.layers.24.mlp.gate", |
| "model.language_model.layers.24.mlp.shared_expert_gate", |
| "model.language_model.layers.24.post_attention_layernorm", |
| "model.language_model.layers.25.input_layernorm", |
| "model.language_model.layers.25.linear_attn", |
| "model.language_model.layers.25.linear_attn.conv1d", |
| "model.language_model.layers.25.linear_attn.in_proj_a", |
| "model.language_model.layers.25.linear_attn.in_proj_b", |
| "model.language_model.layers.25.linear_attn.norm", |
| "model.language_model.layers.25.mlp.gate", |
| "model.language_model.layers.25.mlp.shared_expert_gate", |
| "model.language_model.layers.25.post_attention_layernorm", |
| "model.language_model.layers.26.input_layernorm", |
| "model.language_model.layers.26.linear_attn", |
| "model.language_model.layers.26.linear_attn.conv1d", |
| "model.language_model.layers.26.linear_attn.in_proj_a", |
| "model.language_model.layers.26.linear_attn.in_proj_b", |
| "model.language_model.layers.26.linear_attn.norm", |
| "model.language_model.layers.26.mlp.gate", |
| "model.language_model.layers.26.mlp.shared_expert_gate", |
| "model.language_model.layers.26.post_attention_layernorm", |
| "model.language_model.layers.27.input_layernorm", |
| "model.language_model.layers.27.mlp.gate", |
| "model.language_model.layers.27.mlp.shared_expert_gate", |
| "model.language_model.layers.27.post_attention_layernorm", |
| "model.language_model.layers.27.self_attn.k_norm", |
| "model.language_model.layers.27.self_attn.q_norm", |
| "model.language_model.layers.28.input_layernorm", |
| "model.language_model.layers.28.linear_attn", |
| "model.language_model.layers.28.linear_attn.conv1d", |
| "model.language_model.layers.28.linear_attn.in_proj_a", |
| "model.language_model.layers.28.linear_attn.in_proj_b", |
| "model.language_model.layers.28.linear_attn.norm", |
| "model.language_model.layers.28.mlp.gate", |
| "model.language_model.layers.28.mlp.shared_expert_gate", |
| "model.language_model.layers.28.post_attention_layernorm", |
| "model.language_model.layers.29.input_layernorm", |
| "model.language_model.layers.29.linear_attn", |
| "model.language_model.layers.29.linear_attn.conv1d", |
| "model.language_model.layers.29.linear_attn.in_proj_a", |
| "model.language_model.layers.29.linear_attn.in_proj_b", |
| "model.language_model.layers.29.linear_attn.norm", |
| "model.language_model.layers.29.mlp.gate", |
| "model.language_model.layers.29.mlp.shared_expert_gate", |
| "model.language_model.layers.29.post_attention_layernorm", |
| "model.language_model.layers.3.input_layernorm", |
| "model.language_model.layers.3.mlp.gate", |
| "model.language_model.layers.3.mlp.shared_expert_gate", |
| "model.language_model.layers.3.post_attention_layernorm", |
| "model.language_model.layers.3.self_attn.k_norm", |
| "model.language_model.layers.3.self_attn.q_norm", |
| "model.language_model.layers.30.input_layernorm", |
| "model.language_model.layers.30.linear_attn", |
| "model.language_model.layers.30.linear_attn.conv1d", |
| "model.language_model.layers.30.linear_attn.in_proj_a", |
| "model.language_model.layers.30.linear_attn.in_proj_b", |
| "model.language_model.layers.30.linear_attn.norm", |
| "model.language_model.layers.30.mlp.gate", |
| "model.language_model.layers.30.mlp.shared_expert_gate", |
| "model.language_model.layers.30.post_attention_layernorm", |
| "model.language_model.layers.31.input_layernorm", |
| "model.language_model.layers.31.mlp.gate", |
| "model.language_model.layers.31.mlp.shared_expert_gate", |
| "model.language_model.layers.31.post_attention_layernorm", |
| "model.language_model.layers.31.self_attn.k_norm", |
| "model.language_model.layers.31.self_attn.q_norm", |
| "model.language_model.layers.32.input_layernorm", |
| "model.language_model.layers.32.linear_attn", |
| "model.language_model.layers.32.linear_attn.conv1d", |
| "model.language_model.layers.32.linear_attn.in_proj_a", |
| "model.language_model.layers.32.linear_attn.in_proj_b", |
| "model.language_model.layers.32.linear_attn.norm", |
| "model.language_model.layers.32.mlp.gate", |
| "model.language_model.layers.32.mlp.shared_expert_gate", |
| "model.language_model.layers.32.post_attention_layernorm", |
| "model.language_model.layers.33.input_layernorm", |
| "model.language_model.layers.33.linear_attn", |
| "model.language_model.layers.33.linear_attn.conv1d", |
| "model.language_model.layers.33.linear_attn.in_proj_a", |
| "model.language_model.layers.33.linear_attn.in_proj_b", |
| "model.language_model.layers.33.linear_attn.norm", |
| "model.language_model.layers.33.mlp.gate", |
| "model.language_model.layers.33.mlp.shared_expert_gate", |
| "model.language_model.layers.33.post_attention_layernorm", |
| "model.language_model.layers.34.input_layernorm", |
| "model.language_model.layers.34.linear_attn", |
| "model.language_model.layers.34.linear_attn.conv1d", |
| "model.language_model.layers.34.linear_attn.in_proj_a", |
| "model.language_model.layers.34.linear_attn.in_proj_b", |
| "model.language_model.layers.34.linear_attn.norm", |
| "model.language_model.layers.34.mlp.gate", |
| "model.language_model.layers.34.mlp.shared_expert_gate", |
| "model.language_model.layers.34.post_attention_layernorm", |
| "model.language_model.layers.35.input_layernorm", |
| "model.language_model.layers.35.mlp.gate", |
| "model.language_model.layers.35.mlp.shared_expert_gate", |
| "model.language_model.layers.35.post_attention_layernorm", |
| "model.language_model.layers.35.self_attn.k_norm", |
| "model.language_model.layers.35.self_attn.q_norm", |
| "model.language_model.layers.36.input_layernorm", |
| "model.language_model.layers.36.linear_attn", |
| "model.language_model.layers.36.linear_attn.conv1d", |
| "model.language_model.layers.36.linear_attn.in_proj_a", |
| "model.language_model.layers.36.linear_attn.in_proj_b", |
| "model.language_model.layers.36.linear_attn.norm", |
| "model.language_model.layers.36.mlp.gate", |
| "model.language_model.layers.36.mlp.shared_expert_gate", |
| "model.language_model.layers.36.post_attention_layernorm", |
| "model.language_model.layers.37.input_layernorm", |
| "model.language_model.layers.37.linear_attn", |
| "model.language_model.layers.37.linear_attn.conv1d", |
| "model.language_model.layers.37.linear_attn.in_proj_a", |
| "model.language_model.layers.37.linear_attn.in_proj_b", |
| "model.language_model.layers.37.linear_attn.norm", |
| "model.language_model.layers.37.mlp.gate", |
| "model.language_model.layers.37.mlp.shared_expert_gate", |
| "model.language_model.layers.37.post_attention_layernorm", |
| "model.language_model.layers.38.input_layernorm", |
| "model.language_model.layers.38.linear_attn", |
| "model.language_model.layers.38.linear_attn.conv1d", |
| "model.language_model.layers.38.linear_attn.in_proj_a", |
| "model.language_model.layers.38.linear_attn.in_proj_b", |
| "model.language_model.layers.38.linear_attn.norm", |
| "model.language_model.layers.38.mlp.gate", |
| "model.language_model.layers.38.mlp.shared_expert_gate", |
| "model.language_model.layers.38.post_attention_layernorm", |
| "model.language_model.layers.39.input_layernorm", |
| "model.language_model.layers.39.mlp.gate", |
| "model.language_model.layers.39.mlp.shared_expert_gate", |
| "model.language_model.layers.39.post_attention_layernorm", |
| "model.language_model.layers.39.self_attn.k_norm", |
| "model.language_model.layers.39.self_attn.q_norm", |
| "model.language_model.layers.4.input_layernorm", |
| "model.language_model.layers.4.linear_attn", |
| "model.language_model.layers.4.linear_attn.conv1d", |
| "model.language_model.layers.4.linear_attn.in_proj_a", |
| "model.language_model.layers.4.linear_attn.in_proj_b", |
| "model.language_model.layers.4.linear_attn.norm", |
| "model.language_model.layers.4.mlp.gate", |
| "model.language_model.layers.4.mlp.shared_expert_gate", |
| "model.language_model.layers.4.post_attention_layernorm", |
| "model.language_model.layers.5.input_layernorm", |
| "model.language_model.layers.5.linear_attn", |
| "model.language_model.layers.5.linear_attn.conv1d", |
| "model.language_model.layers.5.linear_attn.in_proj_a", |
| "model.language_model.layers.5.linear_attn.in_proj_b", |
| "model.language_model.layers.5.linear_attn.norm", |
| "model.language_model.layers.5.mlp.gate", |
| "model.language_model.layers.5.mlp.shared_expert_gate", |
| "model.language_model.layers.5.post_attention_layernorm", |
| "model.language_model.layers.6.input_layernorm", |
| "model.language_model.layers.6.linear_attn", |
| "model.language_model.layers.6.linear_attn.conv1d", |
| "model.language_model.layers.6.linear_attn.in_proj_a", |
| "model.language_model.layers.6.linear_attn.in_proj_b", |
| "model.language_model.layers.6.linear_attn.norm", |
| "model.language_model.layers.6.mlp.gate", |
| "model.language_model.layers.6.mlp.shared_expert_gate", |
| "model.language_model.layers.6.post_attention_layernorm", |
| "model.language_model.layers.7.input_layernorm", |
| "model.language_model.layers.7.mlp.gate", |
| "model.language_model.layers.7.mlp.shared_expert_gate", |
| "model.language_model.layers.7.post_attention_layernorm", |
| "model.language_model.layers.7.self_attn.k_norm", |
| "model.language_model.layers.7.self_attn.q_norm", |
| "model.language_model.layers.8.input_layernorm", |
| "model.language_model.layers.8.linear_attn", |
| "model.language_model.layers.8.linear_attn.conv1d", |
| "model.language_model.layers.8.linear_attn.in_proj_a", |
| "model.language_model.layers.8.linear_attn.in_proj_b", |
| "model.language_model.layers.8.linear_attn.norm", |
| "model.language_model.layers.8.mlp.gate", |
| "model.language_model.layers.8.mlp.shared_expert_gate", |
| "model.language_model.layers.8.post_attention_layernorm", |
| "model.language_model.layers.9.input_layernorm", |
| "model.language_model.layers.9.linear_attn", |
| "model.language_model.layers.9.linear_attn.conv1d", |
| "model.language_model.layers.9.linear_attn.in_proj_a", |
| "model.language_model.layers.9.linear_attn.in_proj_b", |
| "model.language_model.layers.9.linear_attn.norm", |
| "model.language_model.layers.9.mlp.gate", |
| "model.language_model.layers.9.mlp.shared_expert_gate", |
| "model.language_model.layers.9.post_attention_layernorm", |
| "model.language_model.norm", |
| "model.visual.blocks.0.attn.proj", |
| "model.visual.blocks.0.attn.qkv", |
| "model.visual.blocks.0.mlp.linear_fc1", |
| "model.visual.blocks.0.mlp.linear_fc2", |
| "model.visual.blocks.0.norm1", |
| "model.visual.blocks.0.norm2", |
| "model.visual.blocks.1.attn.proj", |
| "model.visual.blocks.1.attn.qkv", |
| "model.visual.blocks.1.mlp.linear_fc1", |
| "model.visual.blocks.1.mlp.linear_fc2", |
| "model.visual.blocks.1.norm1", |
| "model.visual.blocks.1.norm2", |
| "model.visual.blocks.10.attn.proj", |
| "model.visual.blocks.10.attn.qkv", |
| "model.visual.blocks.10.mlp.linear_fc1", |
| "model.visual.blocks.10.mlp.linear_fc2", |
| "model.visual.blocks.10.norm1", |
| "model.visual.blocks.10.norm2", |
| "model.visual.blocks.11.attn.proj", |
| "model.visual.blocks.11.attn.qkv", |
| "model.visual.blocks.11.mlp.linear_fc1", |
| "model.visual.blocks.11.mlp.linear_fc2", |
| "model.visual.blocks.11.norm1", |
| "model.visual.blocks.11.norm2", |
| "model.visual.blocks.12.attn.proj", |
| "model.visual.blocks.12.attn.qkv", |
| "model.visual.blocks.12.mlp.linear_fc1", |
| "model.visual.blocks.12.mlp.linear_fc2", |
| "model.visual.blocks.12.norm1", |
| "model.visual.blocks.12.norm2", |
| "model.visual.blocks.13.attn.proj", |
| "model.visual.blocks.13.attn.qkv", |
| "model.visual.blocks.13.mlp.linear_fc1", |
| "model.visual.blocks.13.mlp.linear_fc2", |
| "model.visual.blocks.13.norm1", |
| "model.visual.blocks.13.norm2", |
| "model.visual.blocks.14.attn.proj", |
| "model.visual.blocks.14.attn.qkv", |
| "model.visual.blocks.14.mlp.linear_fc1", |
| "model.visual.blocks.14.mlp.linear_fc2", |
| "model.visual.blocks.14.norm1", |
| "model.visual.blocks.14.norm2", |
| "model.visual.blocks.15.attn.proj", |
| "model.visual.blocks.15.attn.qkv", |
| "model.visual.blocks.15.mlp.linear_fc1", |
| "model.visual.blocks.15.mlp.linear_fc2", |
| "model.visual.blocks.15.norm1", |
| "model.visual.blocks.15.norm2", |
| "model.visual.blocks.16.attn.proj", |
| "model.visual.blocks.16.attn.qkv", |
| "model.visual.blocks.16.mlp.linear_fc1", |
| "model.visual.blocks.16.mlp.linear_fc2", |
| "model.visual.blocks.16.norm1", |
| "model.visual.blocks.16.norm2", |
| "model.visual.blocks.17.attn.proj", |
| "model.visual.blocks.17.attn.qkv", |
| "model.visual.blocks.17.mlp.linear_fc1", |
| "model.visual.blocks.17.mlp.linear_fc2", |
| "model.visual.blocks.17.norm1", |
| "model.visual.blocks.17.norm2", |
| "model.visual.blocks.18.attn.proj", |
| "model.visual.blocks.18.attn.qkv", |
| "model.visual.blocks.18.mlp.linear_fc1", |
| "model.visual.blocks.18.mlp.linear_fc2", |
| "model.visual.blocks.18.norm1", |
| "model.visual.blocks.18.norm2", |
| "model.visual.blocks.19.attn.proj", |
| "model.visual.blocks.19.attn.qkv", |
| "model.visual.blocks.19.mlp.linear_fc1", |
| "model.visual.blocks.19.mlp.linear_fc2", |
| "model.visual.blocks.19.norm1", |
| "model.visual.blocks.19.norm2", |
| "model.visual.blocks.2.attn.proj", |
| "model.visual.blocks.2.attn.qkv", |
| "model.visual.blocks.2.mlp.linear_fc1", |
| "model.visual.blocks.2.mlp.linear_fc2", |
| "model.visual.blocks.2.norm1", |
| "model.visual.blocks.2.norm2", |
| "model.visual.blocks.20.attn.proj", |
| "model.visual.blocks.20.attn.qkv", |
| "model.visual.blocks.20.mlp.linear_fc1", |
| "model.visual.blocks.20.mlp.linear_fc2", |
| "model.visual.blocks.20.norm1", |
| "model.visual.blocks.20.norm2", |
| "model.visual.blocks.21.attn.proj", |
| "model.visual.blocks.21.attn.qkv", |
| "model.visual.blocks.21.mlp.linear_fc1", |
| "model.visual.blocks.21.mlp.linear_fc2", |
| "model.visual.blocks.21.norm1", |
| "model.visual.blocks.21.norm2", |
| "model.visual.blocks.22.attn.proj", |
| "model.visual.blocks.22.attn.qkv", |
| "model.visual.blocks.22.mlp.linear_fc1", |
| "model.visual.blocks.22.mlp.linear_fc2", |
| "model.visual.blocks.22.norm1", |
| "model.visual.blocks.22.norm2", |
| "model.visual.blocks.23.attn.proj", |
| "model.visual.blocks.23.attn.qkv", |
| "model.visual.blocks.23.mlp.linear_fc1", |
| "model.visual.blocks.23.mlp.linear_fc2", |
| "model.visual.blocks.23.norm1", |
| "model.visual.blocks.23.norm2", |
| "model.visual.blocks.24.attn.proj", |
| "model.visual.blocks.24.attn.qkv", |
| "model.visual.blocks.24.mlp.linear_fc1", |
| "model.visual.blocks.24.mlp.linear_fc2", |
| "model.visual.blocks.24.norm1", |
| "model.visual.blocks.24.norm2", |
| "model.visual.blocks.25.attn.proj", |
| "model.visual.blocks.25.attn.qkv", |
| "model.visual.blocks.25.mlp.linear_fc1", |
| "model.visual.blocks.25.mlp.linear_fc2", |
| "model.visual.blocks.25.norm1", |
| "model.visual.blocks.25.norm2", |
| "model.visual.blocks.26.attn.proj", |
| "model.visual.blocks.26.attn.qkv", |
| "model.visual.blocks.26.mlp.linear_fc1", |
| "model.visual.blocks.26.mlp.linear_fc2", |
| "model.visual.blocks.26.norm1", |
| "model.visual.blocks.26.norm2", |
| "model.visual.blocks.3.attn.proj", |
| "model.visual.blocks.3.attn.qkv", |
| "model.visual.blocks.3.mlp.linear_fc1", |
| "model.visual.blocks.3.mlp.linear_fc2", |
| "model.visual.blocks.3.norm1", |
| "model.visual.blocks.3.norm2", |
| "model.visual.blocks.4.attn.proj", |
| "model.visual.blocks.4.attn.qkv", |
| "model.visual.blocks.4.mlp.linear_fc1", |
| "model.visual.blocks.4.mlp.linear_fc2", |
| "model.visual.blocks.4.norm1", |
| "model.visual.blocks.4.norm2", |
| "model.visual.blocks.5.attn.proj", |
| "model.visual.blocks.5.attn.qkv", |
| "model.visual.blocks.5.mlp.linear_fc1", |
| "model.visual.blocks.5.mlp.linear_fc2", |
| "model.visual.blocks.5.norm1", |
| "model.visual.blocks.5.norm2", |
| "model.visual.blocks.6.attn.proj", |
| "model.visual.blocks.6.attn.qkv", |
| "model.visual.blocks.6.mlp.linear_fc1", |
| "model.visual.blocks.6.mlp.linear_fc2", |
| "model.visual.blocks.6.norm1", |
| "model.visual.blocks.6.norm2", |
| "model.visual.blocks.7.attn.proj", |
| "model.visual.blocks.7.attn.qkv", |
| "model.visual.blocks.7.mlp.linear_fc1", |
| "model.visual.blocks.7.mlp.linear_fc2", |
| "model.visual.blocks.7.norm1", |
| "model.visual.blocks.7.norm2", |
| "model.visual.blocks.8.attn.proj", |
| "model.visual.blocks.8.attn.qkv", |
| "model.visual.blocks.8.mlp.linear_fc1", |
| "model.visual.blocks.8.mlp.linear_fc2", |
| "model.visual.blocks.8.norm1", |
| "model.visual.blocks.8.norm2", |
| "model.visual.blocks.9.attn.proj", |
| "model.visual.blocks.9.attn.qkv", |
| "model.visual.blocks.9.mlp.linear_fc1", |
| "model.visual.blocks.9.mlp.linear_fc2", |
| "model.visual.blocks.9.norm1", |
| "model.visual.blocks.9.norm2", |
| "model.visual.merger.linear_fc1", |
| "model.visual.merger.linear_fc2", |
| "model.visual.merger.norm", |
| "model.visual.patch_embed.proj", |
| "model.visual.pos_embed", |
| "mtp.fc", |
| "mtp.layers.0.input_layernorm", |
| "mtp.layers.0.mlp.gate", |
| "mtp.layers.0.mlp.shared_expert_gate", |
| "mtp.layers.0.post_attention_layernorm", |
| "mtp.layers.0.self_attn.k_norm", |
| "mtp.layers.0.self_attn.q_norm", |
| "mtp.norm", |
| "mtp.pre_fc_norm_embedding", |
| "mtp.pre_fc_norm_hidden" |
| ] |
| } |
| } |
